Hugging Face's logo

vikp
/
layout_segmenter

Token Classification
Transformers
PyTorch
layoutlmv3
Inference Endpoints
Model card Files Community
3
vikp commited on
Commit
6fea543
•
1 Parent(s): 4c6c15d

Upload processor

Browse files
Files changed (7) hide show
  1. added_tokens.json +7 -0
  2. merges.txt +0 -0
  3. preprocessor_config.json +27 -0
  4. special_tokens_map.json +16 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +86 -0
  7. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 50264,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "LayoutLMv3FeatureExtractor",
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "LayoutLMv3ImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "ocr_lang": null,
19
+ "processor_class": "LayoutLMv3Processor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 224,
24
+ "width": 224
25
+ },
26
+ "tesseract_config": ""
27
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>",
4
+ "<pad>",
5
+ "</s>",
6
+ "<unk>",
7
+ "<mask>"
8
+ ],
9
+ "bos_token": "<s>",
10
+ "cls_token": "<s>",
11
+ "eos_token": "</s>",
12
+ "mask_token": "<mask>",
13
+ "pad_token": "<pad>",
14
+ "sep_token": "</s>",
15
+ "unk_token": "<unk>"
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [
46
+ "<s>",
47
+ "<pad>",
48
+ "</s>",
49
+ "<unk>",
50
+ "<mask>"
51
+ ],
52
+ "apply_ocr": false,
53
+ "bos_token": "<s>",
54
+ "clean_up_tokenization_spaces": true,
55
+ "cls_token": "<s>",
56
+ "cls_token_box": [
57
+ 0,
58
+ 0,
59
+ 0,
60
+ 0
61
+ ],
62
+ "eos_token": "</s>",
63
+ "errors": "replace",
64
+ "mask_token": "<mask>",
65
+ "model_max_length": 512,
66
+ "only_label_first_subword": true,
67
+ "pad_token": "<pad>",
68
+ "pad_token_box": [
69
+ 0,
70
+ 0,
71
+ 0,
72
+ 0
73
+ ],
74
+ "pad_token_label": -100,
75
+ "processor_class": "LayoutLMv3Processor",
76
+ "sep_token": "</s>",
77
+ "sep_token_box": [
78
+ 0,
79
+ 0,
80
+ 0,
81
+ 0
82
+ ],
83
+ "tokenizer_class": "LayoutLMv3Tokenizer",
84
+ "trim_offsets": true,
85
+ "unk_token": "<unk>"
86
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff